Triple
T19593493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wei He |
E470293
|
entity |
| Predicate | romanization |
P2508
|
FINISHED |
| Object | Wei He |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Wei He | Statement: [Wei He, romanization, Wei He]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wei He Context triple: [Wei He, romanization, Wei He]
-
A.
Wei He
chosen
Wei He is the Chinese name for the Wei River, a major tributary of the Yellow River that flows through the historical heartland of ancient Chinese civilization in Shaanxi province.
-
B.
Yuan Weishi
Yuan Weishi is a Chinese historian and public intellectual known for his critical examinations of modern Chinese history and education.
-
C.
Yang Ye
Yang Ye was a famed Song dynasty military general and folk hero of the Yang clan, celebrated in Chinese history and legend for his loyalty and battlefield prowess.
-
D.
Liu Ye
Liu Ye is a Chinese actor known for his versatile performances in both commercial blockbusters and critically acclaimed films.
-
E.
Wang Zhen
Wang Zhen was a prominent Ming dynasty military commander known for his role in the frontier wars against Mongol forces.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640782e2c8190b5baef07a2bdd015 |
completed | April 20, 2026, 3:04 p.m. |
Created at: April 10, 2026, 1:43 p.m.